develop / app.py
minhho's picture
Update code
4eaf505
raw
history blame
1.15 kB
import gradio
from transformers import pipeline
def merge_split_token(tokens):
merged = []
for token in tokens:
if token["word"].startswith('##'):
merged[-1]["word"] += token["word"][2:]
else:
merged.append(token)
return merged
def process_trans_text(text):
nlp=pipeline("ner", model='KBLab/bert-base-swedish-cased-ner', tokenizer='KBLab/bert-base-swedish-cased-ner')
nlp_results = nlp(text)
print('nlp_results:', nlp_results)
nlp_results_merge = merge_split_token(nlp_results)
nlp_results_adjusted = map(lambda entity: dict(entity, **{ 'score': float(entity['score']) }), nlp_results_merge)
print('nlp_results_adjusted:', nlp_results_adjusted)
# Return values
return {'entities': list(nlp_results_adjusted)}
gradio_intreface = gradio.Interface(
fn=process_trans_text,
inputs="text",
outputs="json",
examples=[
["Jag heter Tom och bor i Stockholm."],
["Groens malmgård är en av Stockholms malmgårdar, belägen vid Malmgårdsvägen 53 på Södermalm i Stockholm."]
],
title="Entity Recognition",
description="Something text",
port=8888
)
gradio_intreface.launch(share=True)